...
  • 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Journal of Hydrology >Integrated approach to model decomposed flow hydrograph using artificial neural network and conceptual techniques
【24h】

Integrated approach to model decomposed flow hydrograph using artificial neural network and conceptual techniques

机译：利用人工神经网络和概念技术对水流分解图进行建模的综合方法

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This paper presents the findings of a study aimed at decomposing a flow hydrograph into different segments based oil physical concepts in a catchment, and modelling different segments using different technique viz. conceptual and artificial neural networks (ANNs). An integrated modelling framework is proposed capable of modelling infiltration, base flow, evapotranspiration, soil moisture accounting, and certain segments of the decomposed flow hydrograph using conceptual techniques and the complex, non-linear, and dynamic rainfall-runoff process using ANN technique. Specifically, five different multi-layer perceptron (MLP) and two self-organizing map (SOM) models have been developed. The rainfall and streamflow data derived from the Kentucky River catchment were employed to test the proposed methodology and develop all the models. The performance of all the models was evaluated using seven different standard statistical measures. The results obtained in this study indicate that (a) the rainfall-runoff relationship in a large catchment consists of at least three or four different mappings corresponding to different dynamics of the underlying physical processes, (b) an integrated approach that models the different segments of the decomposed flow hydrogaph using different techniques is better than a single ANN in modelling the complex, dynamic, non-linear, and fragmented rainfall runoff process, (c) a simple model based on the concept of flow recession is better than an ANN to model the falling limb of a flow hydrograph, and (d) decomposing a flow hydrograph into the different segments corresponding to the different dynamics based on the physical concepts is better than using the soft decomposition employed using SOM. (c) 2005 Elsevier B.V. All rights reserved.
机译：本文介绍了一项旨在将流水线图分解为流域中基于石油物理概念的不同段，并使用不同技术对不同段进行建模的研究结果。概念和人工神经网络（ANN）。提出了一个集成的建模框架，该框架能够使用概念技术以及使用ANN技术的复杂，非线性和动态降雨-径流过程来模拟入渗，基础流量，蒸散量，土壤湿度核算以及分解流水线的某些部分。具体来说，已经开发了五个不同的多层感知器（MLP）和两个自组织映射（SOM）模型。来自肯塔基河流域的降雨和流量数据被用来测试所提出的方法并开发所有模型。使用七个不同的标准统计量度评估了所有模型的性能。这项研究获得的结果表明：（a）大流域的降雨-径流关系至少包含三个或四个不同的映射，分别对应于基础物理过程的不同动态，（b）为不同部分建模的综合方法在复杂，动态，非线性和零碎的降雨径流过程建模中，使用不同技术分解的水文水文优于单一的人工神经网络。（c）基于水流衰退概念的简单模型优于人工神经网络。对流水线图的下降肢进行建模，并且（d）基于物理概念将流水线图分解为与不同动力学相对应的不同段，比使用SOM所采用的软分解更好。 （c）2005 Elsevier B.V.保留所有权利。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号